A safety detection method for boiler flue gas waste heat recovery power system

Abstract

The present invention discloses a safety detection method for a boiler flue gas waste heat recovery power system, which specifically relates to the technical field of flue gas waste heat recovery, and comprises the following steps: acquiring and marking information of each safety component, detecting its operating efficiency in real time, obtaining the operating efficiency fluctuation rate and flow rate drop rate of each component by analysis, calculating the operating quality coefficient, dividing the components into normal and abnormal operating states, adjusting the detection frequency of components in normal operating states, performing abnormal analysis on components in abnormal operating states, judging the maintenance or update method, generating an adjustment form by corresponding the detection frequency adjustment result with the component marking information, and generating a safe operation and maintenance form by summarizing the marking information of the abnormal component with the safe operation and maintenance method; the present invention improves the accuracy and reliability of the detection data by selecting the most suitable efficiency calculation method, so that the detection result can truly reflect the operating state of the component, optimizes the detection and maintenance strategy, and improves the overall operating efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of flue gas waste heat recovery, and more specifically, to a safety detection method for a boiler flue gas waste heat recovery power system. Background Art

[0002] In modern industrial processes, the boiler flue gas waste heat recovery power system is an important energy recovery and utilization device. Its main function is to recover waste heat from the high-temperature flue gas discharged by the boiler and convert it into usable energy, thereby improving energy utilization efficiency and reducing energy consumption and environmental pollution. The safety inspection of the boiler flue gas waste heat recovery power system refers to the safety assessment and inspection of the system that recovers waste heat from the flue gas discharged by the boiler and converts it into power. This includes the inspection of various components in the system, such as heat exchangers, pipes, pumps and valves, to ensure that they can operate safely under high temperature and high pressure conditions.

[0003] The existing technology has the following shortcomings: the existing detection methods often rely on a single efficiency calculation method, which is prone to incompatibility with the actual state of the boiler flue gas waste heat recovery power system under different operating conditions, reducing the reliability of the final decision data. The maintenance strategy lacks a dynamic adjustment mechanism and cannot be adjusted in time according to the actual operating status, resulting in waste of maintenance resources and unnecessary downtime. Maintenance and update operations are often based on fixed time intervals and cannot be flexibly adjusted according to actual conditions, resulting in reduced economic benefits. Therefore, a boiler flue gas waste heat recovery power system safety detection method is proposed herein. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for detecting safety of a boiler flue gas waste heat recovery power system comprises the following steps:

[0006] Obtain information on each safety component in the boiler flue gas waste heat recovery power system, and mark all safety components. During the operation of the boiler flue gas waste heat recovery power system, detect its operating efficiency in real time, conduct preliminary analysis on each safety component, and obtain the operating efficiency fluctuation rate and flow rate drop rate of each component;

[0007] Based on the operating efficiency fluctuation rate and the flow rate drop rate, the target components are comprehensively analyzed to obtain the operating quality coefficient, and the target components are divided into normal operating state and abnormal operating state according to the operating quality coefficient;

[0008] Adjust the detection frequency of components in normal operation and perform abnormal analysis on components in abnormal operation to obtain abnormal maintenance cost coefficients, and determine the safe operation and maintenance method for maintenance or update based on the abnormal maintenance cost coefficients;

[0009] All detection frequency adjustment results are matched one by one with the marking information of components in normal operating state and an adjustment form is generated. All marking information of components in abnormal operating state and their corresponding safe operation and maintenance methods are summarized and a safe operation and maintenance form is generated.

[0010] In a preferred embodiment, the steps of performing a preliminary analysis on the security component are as follows:

[0011] Get the time series data of the operating efficiency of the target security component within a fixed time window: , , …, ; n is the total number of operating efficiencies detected, then the mean and standard deviation of the time series data of the operating efficiency are calculated, and then substituted into the operating efficiency volatility calculation formula: ; represents the operating efficiency fluctuation rate, The standard deviation of the time series data representing the operating efficiency, The average value of the time series data representing the operating efficiency;

[0012] Record the total fluid flow L1 passing through the target safety component at the start of the detection time of the fixed time window and the total fluid flow L2 passing through the target safety component at the end of the detection time, and subtract the total fluid flow L1 passing through the target safety component at the start of the detection time from the total fluid flow L2 passing through the target safety component at the end of the detection time to obtain the flow difference , the flow difference Divide by the time period of the fixed-length window to get the traffic drop rate.

[0013] In a preferred embodiment, the logic of comprehensive analysis of the target component is:

[0014] The operating efficiency fluctuation rate and traffic drop rate of the target component are obtained, and the operating efficiency fluctuation rate and traffic drop rate of the target component are substituted into the pre-trained machine learning model to obtain the operating quality coefficient.

[0015] In a preferred embodiment, the logic of dividing the target component into a normal operating state and an abnormal operating state according to the operating quality coefficient is:

[0016] Obtain the operating quality coefficient of the target component, and then compare it with the preset operating state classification threshold. If the operating quality coefficient is greater than or equal to the preset operating state classification threshold, the target component is classified as a normal operating state. If the operating quality coefficient is less than the preset operating state classification threshold, the target component is classified as an abnormal operating state.

[0017] In a preferred embodiment, adjusting the detection frequency of a component in a normal operating state refers to:

[0018] Get the basic detection frequency of the component in normal operation state, the number of times it is continuously divided into normal operation state, and then calculate the adjusted detection frequency. The calculation formula is: ; TZ represents the adjusted detection frequency, JC represents the basic detection frequency of the component in normal operating state, m is the number of times it is continuously divided into normal operating state, and C is a constant.

[0019] In a preferred embodiment, abnormal analysis is performed on components in abnormal operating states, and the abnormal maintenance cost coefficient is obtained as follows:

[0020] The actual data of various operating parameters of the target component in abnormal operating state and its operating quality coefficient are obtained, and the actual data of various operating parameters and the operating quality coefficient are summarized to obtain vector one, and then the preset operating quality threshold and the standard operating range of each operating parameter are obtained, and the average value of the standard operating range of each operating parameter is calculated respectively, and then the standard average value of each operating parameter and the preset operating quality threshold are summarized to obtain vector two, and the Euclidean distance calculation method is used to calculate vector two and vector one to obtain the abnormal maintenance cost coefficient.

[0021] In a preferred embodiment, the determination of the safe operation and maintenance mode for maintenance or updating based on the abnormal maintenance cost coefficient refers to:

[0022] Obtain the abnormal maintenance cost coefficient of the target component in abnormal operation state and the preset target benefit value, and calculate the cost value of maintaining it: ; YC is the abnormal maintenance cost coefficient of the target component in abnormal operating state, GH is the cost required for replacement, CB is the cost value spent on maintenance, and the cost value CB is compared with the preset target benefit value. If the cost value CB is greater than or equal to the preset target benefit value, the safe operation and maintenance method adopted is update. If the cost value CB is less than the preset target benefit value, the safe operation and maintenance method adopted is maintenance.

[0023] In a preferred embodiment, there are n types of operation efficiency detection preset. Before preliminary analysis of each safety component, it is necessary to analyze the adopted operation efficiency detection type. The logic is as follows:

[0024] The data of n different efficiency calculation methods under different operating conditions of the boiler flue gas waste heat recovery power system were collected and sorted out to obtain n groups of efficiency data groups. The mean of each group and the total mean of the n groups of efficiency data groups were calculated respectively. Then, the inter-group variance reflecting the difference between the group means and the intra-group variance reflecting the difference within each group were calculated. The inter-group degrees of freedom and the intra-group degrees of freedom were calculated, and finally the F value was calculated. The calculation formula is: ; MSB represents the mean square between groups, and the calculation formula is: ; It represents the degrees of freedom between groups, which is obtained by subtracting one from the number of groups n. MSW represents the mean square within the group, and the calculation formula is: ; It represents the degrees of freedom within the group. The degrees of freedom within the group are obtained by subtracting the number of groups n from the total number of samples. According to the calculated F value, the degrees of freedom between groups, and the degrees of freedom within the group, the corresponding P value in the F distribution table is found. If the P value is less than the significance level, the differences between different groups are considered significant. Otherwise, the differences between different groups are considered insignificant.

[0025] In a preferred embodiment, based on the difference analysis results between different groups, the type of detection of operating efficiency to be adopted is determined:

[0026] If the P value is less than the significance level, calculate the coefficient of variation of the operating efficiency corresponding to each detection type. The coefficient of variation is the ratio of the standard deviation of the detected data to the mean, and select the detection type of operating efficiency corresponding to the minimum coefficient of variation.

[0027] If the P value is not less than the significance level, any one of the n types of operating efficiency detection is selected.

[0028] Technical effects and advantages of the present invention:

[0029] The present invention performs real-time detection and comprehensive analysis on various safety components in the boiler flue gas waste heat recovery power system, and adjusts the maintenance and detection frequency according to the analysis results. By selecting the most suitable efficiency calculation method, the accuracy and reliability of the detection data are improved, so that the detection results can truly reflect the operating status of the components. The significance test and coefficient of variation calculation based on statistical analysis are used to ensure that the selected detection type has good adaptability under different operating conditions.

[0030] The present invention dynamically adjusts the detection frequency according to the operating status, reduces the detection frequency for components that have been operating normally for a long time, concentrates resources to detect components with more potential problems, optimizes resource allocation, and improves detection efficiency. By calculating the abnormal maintenance cost coefficient, it reasonably determines whether to perform maintenance or update, avoids unnecessary maintenance operations, and reduces maintenance costs. Through real-time detection and comprehensive analysis, components in abnormal operating states are discovered and processed in time to prevent the occurrence of potential failures, thereby enhancing the stability and security of the system, providing data-driven decision support, and helping managers make more scientific and effective maintenance decisions to ensure the long-term stable operation of the system.

[0031] The present invention reduces unnecessary downtime and maintenance operations by optimizing detection and maintenance strategies, thereby improving the overall operating efficiency of the system. Based on the judgment method of economic benefits, it ensures that each maintenance and update operation can bring actual economic benefits, thereby improving the economic operation level of the system. By dynamically adjusting the detection frequency and maintenance strategy, it can flexibly respond to changes in the system's operating status and maintain the system's optimal performance under different operating conditions. It realizes the scientific selection of different operating efficiency calculation methods, thereby ensuring that high-quality detection data can be obtained under various operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0033] Figure 1 The schematic diagram is a safety detection method for a boiler flue gas waste heat recovery power system in the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Reference Figure 1 The following examples are obtained:

[0036] Embodiment 1: A method for detecting safety of a boiler flue gas waste heat recovery power system, comprising the following steps:

[0037] Obtain information about each safety component in the boiler flue gas waste heat recovery power system and mark all safety components. During the operation of the boiler flue gas waste heat recovery power system, detect its operating efficiency in real time, conduct preliminary analysis on each safety component, and obtain the operating efficiency fluctuation rate and flow rate drop rate of each component; collect and record the unique identifier of each safety component, such as serial number or equipment ID, location information, model, etc.;

[0038] Based on the operating efficiency fluctuation rate and the flow rate drop rate, the target components are comprehensively analyzed to obtain the operating quality coefficient, and the target components are divided into normal operating state and abnormal operating state according to the operating quality coefficient;

[0039] Adjust the detection frequency of components in normal operation and perform abnormal analysis on components in abnormal operation to obtain abnormal maintenance cost coefficients, and determine the safe operation and maintenance method for maintenance or update based on the abnormal maintenance cost coefficients;

[0040] All detection frequency adjustment results are matched one by one with the marking information of components in normal operating state and an adjustment form is generated. The marking information of all components in abnormal operating state and their corresponding safe operation and maintenance methods are summarized and a safe operation and maintenance form is generated; adjustment form: contains the detection frequency adjustment results and the marking information of components in normal operating state, safe operation and maintenance form: contains the marking information of components in abnormal operating state and their corresponding safe operation and maintenance methods.

[0041] Delayed maintenance and updates in boiler flue gas waste heat recovery power systems can lead to the following problems:

[0042] Accumulation of safety hazards: As time goes by, equipment and systems will gradually age and wear out. If they are not maintained and updated in a timely manner, potential safety hazards will continue to accumulate. This may lead to serious accidents such as leakage and explosion in the system under high temperature and high pressure environments.

[0043] Degraded system performance: Delayed maintenance and updates will lead to reduced efficiency of key system components such as heat exchangers, pipes, valves, etc. This will not only affect the overall performance of the system, but may also lead to increased energy consumption and reduce the effect of waste heat recovery, thus failing to achieve the goal of energy conservation and emission reduction.

[0044] Increased failure rate: Long-term lack of maintenance of equipment is prone to failure and damage, resulting in increased frequency of system shutdowns for maintenance. Frequent failures not only affect production efficiency, but may also increase maintenance costs.

[0045] Insufficient ability to deal with new problems: With the development of technology and changes in the system operating environment, new problems and challenges will continue to emerge. If maintenance and updates lag behind, the system will not be able to adapt and respond to these changes in a timely manner, which may result in some new problems not being effectively solved, affecting the long-term stable operation of the system.

[0046] Delayed maintenance and updates can indeed lead to a decline in the efficiency of key system components such as heat exchangers, pipes, valves, etc. for the following reasons:

[0047] Fouling and clogging: Heat exchangers: Dirt, corrosion products and sediments will gradually accumulate on the surface of heat exchangers. These impurities will reduce the efficiency of heat exchange, hinder the transfer of heat, and make the system require more energy to achieve the same effect. Pipes: Dirt and corrosion products may accumulate on the inner wall of the pipe, resulting in poor fluid flow, increased flow resistance, and reduced fluid transmission efficiency. Valves: Sediments and corrosion products on the valve will affect its sealing performance and operational flexibility, causing the valve to be unable to fully open or close, affecting the control of the fluid and the overall efficiency of the system.

[0048] Corrosion and wear: Heat exchangers: Heat exchangers that have not been maintained for a long time will corrode due to chemical reactions in high temperature and high pressure environments, causing the heat exchange tube wall to become thinner, leak or even rupture, seriously affecting the heat exchange efficiency. Pipelines: Pipelines are also affected by corrosion and wear, especially when transmitting corrosive media. The corrosion of the pipe wall will increase the risk of fluid leakage and flow resistance, and reduce the transmission efficiency. Valves: The sealing surface and valve stem of the valve will wear out during long-term use, resulting in reduced sealing performance and inflexible operation, which in turn affects the control accuracy and efficiency of the system.

[0049] Mechanical failure and fatigue: Heat exchangers: Heat exchangers in long-term operation are affected by thermal and mechanical stresses, which may cause material fatigue and structural damage, reducing their working efficiency and reliability. Pipelines: Pipelines may deform, crack and fatigue damage after long-term use under high temperature and high pressure, increasing system operation resistance and leakage risks. Valves: Mechanical parts of valves such as springs and sealing rings will age and be damaged during long-term use, affecting their opening and closing functions and sealing performance, thereby reducing system efficiency.

[0050] The steps for preliminary analysis of safety components are as follows: Examples of safety components are: heat exchangers, pipes, valves, etc., and the time series data of the operating efficiency of the target safety components is obtained within a fixed time window: , ,…, ; n is the total number of operating efficiencies detected, then the mean and standard deviation of the time series data of the operating efficiency are calculated, and then substituted into the operating efficiency volatility calculation formula: ; represents the operating efficiency fluctuation rate, The standard deviation of the time series data representing the operating efficiency, The average value of the time series data showing the operating efficiency;

[0051] Record the total fluid flow L1 passing through the target safety component at the start of the detection time of the fixed time window and the total fluid flow L2 passing through the target safety component at the end of the detection time, and subtract the total fluid flow L1 passing through the target safety component at the start of the detection time from the total fluid flow L2 passing through the target safety component at the end of the detection time to obtain the flow difference , the flow difference Divide by the time period of the fixed-length window to get the traffic drop rate.

[0052] The logic of comprehensive analysis of target components is:

[0053] The operating efficiency fluctuation rate and flow rate drop rate of the target component are obtained, and the operating efficiency fluctuation rate and flow rate drop rate of the target component are substituted into the pre-trained machine learning model to obtain the operating quality coefficient. The machine learning model is not specifically specified, and a model that can generate the operating quality coefficient by comprehensively analyzing the operating efficiency fluctuation rate and flow rate drop rate of the target component can be used. The present invention provides a specific implementation method: for example, the operating efficiency fluctuation rate and flow rate drop rate of the target component are standardized respectively, and the processing method is exemplified by Z-score standardization, and then a weight coefficient is assigned to the standardized operating efficiency fluctuation rate and flow rate drop rate, and then the product of the two and the weight coefficient is calculated, and then the sum of the two product values ​​is calculated to be the operating quality coefficient. The operating quality coefficient is a comprehensive indicator used to evaluate the overall performance and quality of the target component during operation. The operating efficiency fluctuation rate refers to the degree of fluctuation of the operating efficiency within a certain period of time, reflecting the stability of the operating efficiency of the target component. The smaller the fluctuation rate, the more stable the operating efficiency. The flow rate drop rate refers to the rate of change of the fluid flow rate within a certain period of time, usually expressed as the change in flow rate per unit time, reflecting the health status of the fluid system. A significant drop in flow rate may indicate blockage, leakage or other performance problems.

[0054] The logic of dividing the target component into normal operating state and abnormal operating state according to the operating quality coefficient is: obtain the operating quality coefficient of the target component, and then compare it with the preset operating state division threshold. If the operating quality coefficient is greater than or equal to the preset operating state division threshold, the target component is divided into a normal operating state; if the operating quality coefficient is less than the preset operating state division threshold, the target component is divided into an abnormal operating state.

[0055] In order to optimize resource allocation and improve detection efficiency, the detection frequency of components in normal operation can be adjusted. By calculating the adjusted detection frequency, the detection frequency of components in long-term normal operation can be reasonably reduced, thereby making more rational use of resources. Adjusting the detection frequency of components in normal operation means:

[0056] Get the basic detection frequency of the component in normal operation state, the number of times it is continuously divided into normal operation state, and then calculate the adjusted detection frequency. The calculation formula is: ; TZ represents the adjusted detection frequency, JC represents the basic detection frequency of components in normal operating state, which refers to the initial detection frequency of components in normal operating state, usually determined by system design and initial evaluation, m is the number of times it is continuously divided into normal operating state, C is a constant, which is used to prevent mathematical problems of logarithmic function when m=0, and adjust the degree of slowdown of detection frequency, and prevent calculation problems when m=0. The larger the value of constant C, the greater the adjustment of detection frequency. By adjusting the detection frequency, the detection frequency of components in long-term normal operation can be reduced, so as to focus resources on components that need more attention and improve detection efficiency. By reducing unnecessary frequent detection, the system load can be reduced, and the service life of the equipment can be extended. The detection frequency is dynamically adjusted according to the actual operating state of the component to ensure that the effectiveness and efficiency of detection are improved without affecting safety and performance.

[0057] The abnormal maintenance cost coefficient obtained by abnormal analysis of components in abnormal operating status is:

[0058] The actual data of each operating parameter of the target component in abnormal operating state and its operating quality coefficient are obtained, and the actual data of each operating parameter and the operating quality coefficient are summarized to obtain vector one, and then the preset operating quality threshold and the standard operating range of each operating parameter are obtained, and the average value of the standard operating range of each operating parameter is calculated respectively, and then the standard average value of each operating parameter and the preset operating quality threshold are summarized to obtain vector two, and the Euclidean distance calculation method is used to calculate vector two and vector one to obtain the abnormal maintenance cost coefficient; the specific calculation formula is: ; n is the total number of operating parameters, i represents the number of the operating parameter, is the actual data in vector 1 for the running parameter number i, is the standard mean value of the running parameter number i in vector 2, represents the actual operating quality coefficient, It represents the preset operation quality threshold. The Euclidean distance is the abnormal maintenance cost coefficient of the component under abnormal operation state. This coefficient reflects the difference between the actual operation state and the standard operation state. The larger the value, the greater the degree of deviation from the standard operation state, which requires higher maintenance cost.

[0059] The safe operation and maintenance method for maintenance or update based on the abnormal maintenance cost coefficient refers to:

[0060] Obtain the abnormal maintenance cost coefficient of the target component in abnormal operation state and the preset target benefit value, and calculate the cost value of maintaining it: ; YC is the abnormal maintenance cost coefficient of the target component in abnormal operating state, GH is the cost required for replacement, CB is the cost value spent on maintenance, and the cost value CB is compared with the preset target benefit value. If the cost value CB is greater than or equal to the preset target benefit value, the safe operation and maintenance method adopted is update. If the cost value CB is less than the preset target benefit value, the safe operation and maintenance method adopted is maintenance; The purpose of judging the safe operation and maintenance method is to decide whether to maintain or update the target component in abnormal operating state based on the abnormal maintenance cost coefficient and the preset target benefit value. The update method is selected because the maintenance cost is too high and it is better to update directly. The maintenance method is selected because the maintenance cost is low and the normal operation of the component can be restored through maintenance. By comparing the maintenance cost with the preset target benefit value, the most economical and efficient operation and maintenance method is determined, which can ensure the normal operation of the system under the most economical conditions, improve the overall operating efficiency and reduce the long-term operation and maintenance costs.

[0061] There are n preset types of operation efficiency detection. Before conducting a preliminary analysis of each security component, it is necessary to analyze the adopted operation efficiency detection type. The logic is as follows:

[0062] Collect and organize the data of n different efficiency calculation methods under different operating conditions of the boiler flue gas waste heat recovery power system, collect the operating data of the target components under different operating conditions, including but not limited to inlet and outlet temperature, flow rate, pressure, etc., and then obtain the heat transfer efficiency, fluid transmission efficiency and control efficiency data under various operating states, and finally obtain n groups of efficiency data groups, calculate the mean of each group and the total mean of n groups of efficiency data groups, ; represents the mean of the i-th group, represents the number of samples in the i-th group, Represents the jth data of the i-th group; ; represents the total mean, N is the total number of samples, n is the number of groups, and then the between-group variance reflecting the difference between group means is calculated: ; and the within-group variance, which reflects the differences within each group: ; Calculate the degrees of freedom between groups and within groups, and finally calculate the F value. The calculation formula is: ; Calculate the degrees of freedom between groups and within groups, and finally calculate the F value. The calculation formula is: ; MSB represents the mean square between groups, and the calculation formula is: ; It represents the degrees of freedom between groups, which is obtained by subtracting one from the number of groups n. MSW represents the mean square within the group, and the calculation formula is: ; It represents the degrees of freedom within the group. The degrees of freedom within the group are obtained by subtracting the number of groups n from the total number of samples. According to the calculated F value, the degrees of freedom between groups and the degrees of freedom within the group, the corresponding P value in the F distribution table is found. If the P value is less than the significance level, which is usually set to 0.05, the difference between different groups is considered to be significant. Otherwise, the difference between different groups is considered to be insignificant. The applicability and significance of different operating efficiency calculation methods in the boiler flue gas waste heat recovery power system can be analyzed to help determine the best detection type. Each operating efficiency detection type corresponds to an efficiency calculation method, including but not limited to heat exchange efficiency, fluid transmission efficiency and control efficiency.

[0063] Based on the difference analysis results between different groups, the type of operating efficiency test to be adopted is determined:

[0064] If the P value is less than the significance level, calculate the coefficient of variation of the operating efficiency corresponding to each detection type. The coefficient of variation is the ratio of the standard deviation of the detected data to the mean, and select the detection type of operating efficiency corresponding to the minimum coefficient of variation. The coefficient of variation is the ratio of the standard deviation to the mean, which reflects the relative volatility of the data. The smaller the coefficient of variation, the smaller the relative volatility of the data, and the more stable the efficiency calculation method. If the P value is not less than the significance level, in this case, the difference between different groups is not significant, and any type of operating efficiency detection type can be selected. Finally, any one of the n types of operating efficiency detection types can be selected. Generally, the detection type with the smallest calculation amount can be selected, so that the calculation speed of the operating efficiency is faster. Different operating efficiency calculation methods are commonly used formulas well known to people in this field, which will not be repeated here.

[0065] Different efficiency calculation methods may give different evaluation results for the operating status of the same component. Choosing the most suitable efficiency calculation method can improve the accuracy and reliability of the data and ensure that the test results reflect the actual operating conditions. The boiler flue gas waste heat recovery power system may show different characteristics under different operating conditions. Choosing a suitable calculation method can better adapt to different operating conditions and improve the sensitivity and effectiveness of detection. By choosing the most suitable efficiency calculation method, unnecessary false alarms and missed alarms can be reduced, thereby optimizing resource use. In this way, energy and resources can be focused on components that really need attention, reducing unnecessary maintenance and inspections, and improving the operating efficiency of the overall system. Reliable test data is the basis for making effective maintenance and optimization decisions. By choosing the most suitable efficiency calculation method, higher quality data support can be provided to help managers make more scientific decisions and improve the safety and stability of the system. Accurate detection and evaluation can help identify components that really need maintenance, avoid unnecessary maintenance operations, and thus reduce maintenance costs. By choosing a suitable efficiency calculation method, misjudgment can be reduced and the pertinence and effectiveness of maintenance work can be improved. Inappropriate efficiency calculation methods may lead to misjudgment of system status, which in turn causes unnecessary downtime and maintenance operations, affecting the stability of the system. By choosing the most appropriate calculation method, you can detect potential problems in a timely manner and take measures to ensure the stable operation of the system.

[0066] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0067] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A boiler flue gas waste heat recovery power system safety detection method, characterized in that: The following steps are involved: Obtain information on each safety component in the boiler flue gas waste heat recovery power system, and mark all safety components. During the operation of the boiler flue gas waste heat recovery power system, detect its operating efficiency in real time, conduct preliminary analysis on each safety component, and obtain the operating efficiency fluctuation rate and flow rate drop rate of each component; Based on the operating efficiency fluctuation rate and the flow rate drop rate, the target components are comprehensively analyzed to obtain the operating quality coefficient, and the target components are divided into normal operating state and abnormal operating state according to the operating quality coefficient; Adjust the detection frequency of components in normal operation and perform abnormal analysis on components in abnormal operation to obtain abnormal maintenance cost coefficients, and determine the safe operation and maintenance method for maintenance or update based on the abnormal maintenance cost coefficients; The results of all detection frequency adjustments are matched one by one with the marking information of components in normal operating state and an adjustment form is generated. The marking information of all components in abnormal operating state and their corresponding safe operation and maintenance methods are summarized and a safe operation and maintenance form is generated. The abnormal maintenance cost coefficient obtained by abnormal analysis of components in abnormal operating status is: The actual data of each operating parameter of the target component in the abnormal operating state and its operating quality coefficient are obtained, and the actual data of each operating parameter and the operating quality coefficient are summarized to obtain vector one, and then the preset operating quality threshold and the standard operating range of each operating parameter are obtained, and the average value of the standard operating range of each operating parameter is calculated respectively, and then the average value of the standard operating range of each operating parameter and the preset operating quality threshold are summarized to obtain vector two, and the Euclidean distance calculation method is used to calculate vector two and vector one to obtain the abnormal maintenance cost coefficient; The safe operation and maintenance method for maintenance or update based on the abnormal maintenance cost coefficient refers to: Obtain the abnormal maintenance cost coefficient of the target component in abnormal operation state and the preset target benefit value, and calculate the cost value of maintaining it: ; YC is the abnormal maintenance cost coefficient of the target component in abnormal operation state, GH is the cost required for replacement, CB is the cost value spent on maintenance, and the cost value CB is compared with the preset target benefit value. If the cost value CB is greater than or equal to the preset target benefit value, the safe operation and maintenance method adopted is update; if the cost value CB is less than the preset target benefit value, the safe operation and maintenance method adopted is maintenance; There are n preset types of operation efficiency detection. Before conducting a preliminary analysis of each security component, it is necessary to analyze the adopted operation efficiency detection type. The logic is as follows: The data of n different efficiency calculation methods under different operating conditions of the boiler flue gas waste heat recovery power system were collected and sorted out to obtain n groups of efficiency data groups. The mean of each group and the total mean of the n groups of efficiency data groups were calculated respectively, and then the inter-group variance SSB reflecting the difference between the group means was calculated. ; represents the mean of the i-th group, represents the number of samples in the i-th group, represents the total mean, and the within-group variance SSW reflects the differences within each group. ; Represents the jth data of the i-th group, calculates the degrees of freedom between groups and within groups, and finally calculates the F value. The calculation formula is: ; MSB represents the mean square between groups, and the calculation formula is: ; represents the between-group degrees of freedom, which is obtained by subtracting one from the number of groups n; MSW represents the mean square within the group, and the calculation formula is: ; It represents the degrees of freedom within the group. The degrees of freedom within the group are obtained by subtracting the number of groups n from the total number of samples. According to the calculated F value, the degrees of freedom between groups, and the degrees of freedom within the group, the corresponding P value in the F distribution table is found. If the P value is less than the significance level, the differences between different groups are considered significant. Otherwise, the differences between different groups are considered insignificant.

2. A boiler flue gas waste heat recovery power system safety detection method according to claim 1, characterized in that: The steps for a preliminary analysis of security components are as follows: Get the time series data of the operating efficiency of the target security component within a fixed time window: ; n is the total number of operating efficiencies detected, then the mean and standard deviation of the time series data of the operating efficiency are calculated, and then substituted into the operating efficiency volatility calculation formula: ; represents the operating efficiency fluctuation rate, The standard deviation of the time series data representing the operating efficiency, The average value of the time series data representing the operating efficiency; Record the total fluid flow L1 passing through the target safety component at the start of the detection time of the fixed time window and the total fluid flow L2 passing through the target safety component at the end of the detection time, and subtract the total fluid flow L1 passing through the target safety component at the start of the detection time from the total fluid flow L2 passing through the target safety component at the end of the detection time to obtain the flow difference , the flow difference Divide by the time period of the fixed-length window to get the traffic drop rate.

3. A boiler flue gas waste heat recovery power system safety detection method according to claim 2, characterized in that: The logic for comprehensive analysis of the target components is: The operating efficiency fluctuation rate and traffic drop rate of the target component are obtained, and the operating efficiency fluctuation rate and traffic drop rate of the target component are substituted into the pre-trained machine learning model to obtain the operating quality coefficient.

4. A boiler flue gas waste heat recovery power system safety detection method according to claim 3, characterized in that: The logic of dividing the target component into normal operating state and abnormal operating state according to the operating quality coefficient is: Obtain the operating quality coefficient of the target component, and then compare it with the preset operating state classification threshold. If the operating quality coefficient is greater than or equal to the preset operating state classification threshold, the target component is classified as a normal operating state. If the operating quality coefficient is less than the preset operating state classification threshold, the target component is classified as an abnormal operating state.

5. A boiler flue gas waste heat recovery power system safety detection method according to claim 4, characterized in that: Adjusting the detection frequency of components in normal operating state means: Get the basic detection frequency of the component in normal operation state, the number of times it is continuously divided into normal operation state, and then calculate the adjusted detection frequency. The calculation formula is: ; TZ represents the adjusted detection frequency, JC represents the basic detection frequency of the component in normal operating state, m is the number of times it is continuously divided into normal operating state, and C is a constant.

6. A boiler flue gas waste heat recovery power system safety detection method according to claim 5, characterized in that: Based on the difference analysis results between different groups, the type of operating efficiency test to be adopted is determined: If the P value is less than the significance level, calculate the coefficient of variation of the operating efficiency corresponding to each detection type. The coefficient of variation is the ratio of the standard deviation of the detected data to the mean, and select the detection type of operating efficiency corresponding to the minimum coefficient of variation; If the P value is not less than the significance level, any one of the n types of operating efficiency detection is selected.

Images